LIDAM Discussion Paper LFIN 2025 / 04 

Authors

Roland Bouillot - Université Catholique de Louvain & Maastricht University 

Bertrand Candelon - Université Catholique de Louvain 

Clemens Kool - Maastricht University 

Abstract

Accurate forecasting constitutes a central objective for policymakers. This paper examines the application of advanced machine-learning techniques to predict the 10-year sovereign bond spreads vis-à-vis the German Bund, employing a novel high-dimensional dataset covering 10 European countries over the period 2008-2025. An exhaustive comparison of predictive performance, both in-sample and out-of-sample, demonstrates that XGBoost delivers the highest degree of accuracy. Building on these forecast-based spreads, we construct fragmentation matrices that capture the extent of asymmetry across euro area sovereign bond markets. Prior to the COVID-19 crisis, results confirm the well-documented clustering between core and peripheral countries. However, since 2023 this segmentation appears to have weakened, as French and Belgian spreads exhibit a synchronous trajectory. These findings contribute to the literature on financial integration and fragmentation within the euro area, offering new insights into the evolving dynamics of sovereign bond markets.

Keywords: Machine Learning, Financial Fragmentation, XGBoost, Sovereign spreads 

[ONGOING WORK]

Authors

Roland Bouillot - Université Catholique de Louvain & Maastricht University 

Bertrand Candelon - Université Catholique de Louvain 

Clemens Kool - Maastricht University 

Abstract

This paper studies the financial fragmentation risk in the Euro area sovereign bond market using a combination of machine learning forecasting and network analysis. By applying the XGBoost model to predict sovereign bond yield spreads and constructing correlation-based networks, our analysis identifies structural patterns of financial fragmentation across different forecast horizons. The results indicate that core Euro area economies -such as Austria, Finland and the Netherlands- exhibit strong co-movements in their sovereign spreads, while peripheral countries -including Greece, Ireland and, at longer horizons, France- display weaker correlations. Network analysis highlights key intermediaries in sovereign risk transmission, with Italy and Greece showing strong linkages, while Ireland and Belgium appear to be disconnected. Additionally, we designed a fragmentation indicator, based on betweenness and closeness centrality, that quantifies the degree of financial segmentation over time. Despite policy efforts to enhance financial integration, our findings suggest that fragmentation remains a persistent feature of the Euro area sovereign bond market.

Keywords: Machine Learning, Financial Fragmentation, Network Centrality, Sovereign Spreads, Euro Area

[ONGOING WORK]

Authors

Roland Bouillot - Université Catholique de Louvain & Maastricht University 

Siavash Mohades - Maastricht University & London Business School

Abstract

The euro area shares a common monetary policy but features persistent cross-country heterogeneity in banking-sector structure and credit conditions. This paper examines whether such heterogeneity generates real fragmentation by altering the transmission of ECB monetary policy shocks to private investment. We combine identified ECB monetary policy shocks (covering conventional and unconventional measures) with quarterly country-sector investment data and estimate impulse responses using panel local projections. To capture structure-dependent transmission, we interact monetary policy shocks with pre-determined measures of credit structure, including bank concentration, non-performing loan ratios, capital adequacy, funding composition, and survey-based credit standards. We then propose an operational measure of investment fragmentation defined as the cross-sectional dispersion of cumulative investment responses to a common shock, and construct a time-varying fragmentation index that can be decomposed into a component explained by credit-structure differences and a residual component attributable to fundamentals and other frictions. The findings aim to contribute to policy discussions on the optimal design of ECB interventions and financial integration strategies, addressing challenges related to economic convergence and monetary policy efficiency within the Euro area.

Keywords: Monetary Policy, Credit Structure, Financial Fragmentation, Euro Area, Bank Lending